<?xml version="1.0" standalone="yes"?>
<Paper uid="P97-1009">
  <Title>Using Syntactic Dependency as Local Context to Resolve Word Sense Ambiguity</Title>
  <Section position="3" start_page="64" end_page="65" type="intro">
    <SectionTitle>
2 Local Context
</SectionTitle>
    <Paragraph position="0"> Psychological experiments show that humans are able to resolve word sense ambiguities given a narrow window of surrounding words (Choueka and Lusignan, 1985). Most WSD algorithms take as input * to be defined in Section 3.1 a polysemous word and its local context. Different systems have different definitions of local contexts. In (Leacock, Towwell, and Voorhees, 1996), the local context of a word is an unordered set of words in the sentence containing the word and the preceding sentence. In (Ng and Lee. 1996), a local context of a word consists of an ordered sequence of 6 surrounding part-of-speech tags, its morphological features, and a set of collocations.</Paragraph>
    <Paragraph position="1"> In our approach, a local context of a word is defined in terms of the syntactic dependencies between the word and other words in the same sentence.</Paragraph>
    <Paragraph position="2"> A dependency relationship (Hudson, 1984; Mel'~uk, 1987) is an asymmetric binary relationship between a word called head (or governor, parent), and another word called modifier (or dependent, daughter). Dependency grammars represent sentence structures as a set of dependency relationships. Normally the dependency relationships form a tree that connects all the words in a sentence. An example dependency structure is shown in (4).</Paragraph>
    <Paragraph position="3"> (4) spec subj /-'~ // the boy chased a brown dog The local context of a word W is a triple that corresponds to a dependency relationship in which W is the head or the modifier: (type word position) where type is the type of the dependency relationship, such as subj (subject), adjn (adjunct), compl (first complement), etc.; word is the word related to W via the dependency relationship; and position can either be head or rood. The position indicates whether word is the head or the modifier in depen- null dency relation. Since a word may be involved in several dependency relationships, each occurrence of a word may have multiple local contexts.</Paragraph>
    <Paragraph position="4"> The local contexts of the two nouns &amp;quot;boy&amp;quot; and &amp;quot;dog&amp;quot; in (4) are as follows (the dependency relations between nouns and their determiners are ignored):</Paragraph>
    <Paragraph position="6"> dog (adjn brown rood) (compl chase head) Using a broad coverage parser to parse a corpus, we construct a Local Context Database. An entry in the database is a pair:</Paragraph>
    <Paragraph position="8"> where Ic is a local context and C(lc) is a set of (word frequency likelihood)-triples. Each triple specifies how often word occurred in lc and the likelihood ratio of lc and word. The likelihood ratio is obtained by treating word and Ic as a bigram and computed with the formula in (Dunning, 1993). The database entry corresponding to Table 1 is as follows: C(/c) -- ((ORG 64 50.4) (plant 14 31.0) ...... (pilot 2 5.37))</Paragraph>
  </Section>
class="xml-element"></Paper>